RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
Abstract
Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based representations often exhibit poor robustness in adversarial settings. In this paper, we introduce RobustSentEmbed, a self-supervised sentence embedding framework designed to improve both generalization and robustness in diverse text representation tasks and against a diverse set of adversarial attacks. Through the generation of high-risk adversarial perturbations and their utilization in a novel objective function, RobustSentEmbed adeptly learns high-quality and robust sentence embeddings. Our experiments confirm the superiority of RobustSentEmbed over state-of-the-art representations. Specifically, Our framework achieves a significant reduction in the success rate of various adversarial attacks, notably reducing the BERTAttack success rate by almost half (from 75.51\% to 38.81\%). The framework also yields improvements of 1.59\% and 0.23\% in semantic textual similarity tasks and various transfer tasks, respectively.
Cite
@article{arxiv.2403.11082,
title = {RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning},
author = {Javad Rafiei Asl and Prajwal Panzade and Eduardo Blanco and Daniel Takabi and Zhipeng Cai},
journal= {arXiv preprint arXiv:2403.11082},
year = {2024}
}
Comments
Accepted at the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings) 2024. [https://openreview.net/forum?id=9dEAg4lJEA]